arXiv:2611.24276v1 Announce Type: new Abstract: LLM serving systems store, offload, and share KV caches, exposing token-level representations to infrastructure operators and co-tenants. Shuffled obfuscation combines secret linear transforms with fresh permutations, claiming secu…
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5451, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
26
When Shuffling Fails: Token Recovery from Obfuscated KV Caches
🅲 hạng C
25
Where the Evidence Lives: Measuring Privacy and Diagnosability of Exported AI-Agent Traces
arXiv:2611.20389v1 Announce Type: new Abstract: Execution traces help diagnose AI-agent failures, but sharing them can expose customer identities. For example, detecting that an agent handled the wrong customer's records requires knowing whether the records belong to the request…
🅲 hạng C
24
Where the Savings Go: The Limits of Hiding Cross-Tenant Cache Hits in LLM Serving
arXiv:2611.20291v1 Announce Type: new Abstract: LLM serving engines cache prompt prefixes; a cache hit skips computation and returns faster, so a shared cache reveals whether others have sent a given text. Per-account salting closes this channel but forgoes cross-tenant reuse an…
🅲 hạng C